Dataset Information

Predictors of mortality and endoscopic intervention in patients with upper gastrointestinal bleeding in the intensive care unit.

ABSTRACT: Background:The outcomes of patients undergoing esophagogastroduodenoscopy (EGD) in the intensive care unit (ICU) for upper gastrointestinal bleeding (UGIB) are not well described. Our aims were to determine predictors of 30-day mortality and endoscopic intervention, and assess the utility of existing clinical-prediction tools for UGIB in this population. Methods:Patients hospitalized in an ICU between 2008 and 2015 who underwent EGD were identified using a validated, machine-learning algorithm. Logistic regression was used to determine factors associated with 30-day mortality and endoscopic intervention. Area under receiver-operating characteristics (AUROC) analysis was used to evaluate established UGIB scoring systems in predicting mortality and endoscopic intervention in patients who presented to the hospital with UGIB. Results:A total of 606 patients underwent EGD for UGIB while admitted to an ICU. The median age of the cohort was 62?years and 55.9% were male. Multivariate analysis revealed that predictors associated with 30-day mortality included American Society of Anesthesiologists (ASA) class (odds ratio [OR] 4.1, 95% confidence interval [CI] 2.2-7.9), Charlson score (OR 1.2, 95% CI 1.0-1.3), and duration from hospital admission to EGD (OR 1.04, 95% CI 1.01-1.07). Rockall, Glasgow-Blatchford, and AIMS65 scores were poorly predictive of endoscopic intervention (AUROC: 0.521, 0.514, and 0.540, respectively) and in-hospital mortality (AUROC: 0.510, 0.568, and 0.506, respectively). Conclusions:Predictors associated with 30-day mortality include ASA classification, Charlson score, and duration in the hospital prior to EGD. Existing risk tools are poorly predictive of clinical outcomes, which highlights the need for a more accurate risk-stratification tool to predict the benefit of intervention within the ICU population.

SUBMITTER: Rao VL

PROVIDER: S-EPMC7434581 | biostudies-literature | 2020 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Predictors of mortality and endoscopic intervention in patients with upper gastrointestinal bleeding in the intensive care unit.

Rao Vijaya L VL Gupta Nina N Swei Eric E Wagner Thomas T Aronsohn Andrew A Reddy K Gautham KG Sengupta Neil N

Gastroenterology report 20200401 4

<h4>Background</h4>The outcomes of patients undergoing esophagogastroduodenoscopy (EGD) in the intensive care unit (ICU) for upper gastrointestinal bleeding (UGIB) are not well described. Our aims were to determine predictors of 30-day mortality and endoscopic intervention, and assess the utility of existing clinical-prediction tools for UGIB in this population.<h4>Methods</h4>Patients hospitalized in an ICU between 2008 and 2015 who underwent EGD were identified using a validated, machine-learn ...[more]

PMID: 32843977

Similar Datasets

Project description:IntroductionThis study aims to construct a mortality prediction model for patients with non-variceal upper gastrointestinal bleeding (NVUGIB) in the intensive care unit (ICU), employing advanced machine learning algorithms. The goal is to identify high-risk populations early, contributing to a deeper understanding of patients with NVUGIB in the ICU.MethodsWe extracted NVUGIB data from the Medical Information Mart for Intensive Care IV (MIMIC-IV, v.2.2) database spanning from 2008 to 2019. Feature selection was conducted through LASSO regression, followed by training models using 11 machine learning methods. The best model was chosen based on the area under the curve (AUC). Subsequently, Shapley additive explanations (SHAP) was employed to elucidate how each factor influenced the model. Finally, a case was randomly selected, and the model was utilized to predict its mortality, demonstrating the practical application of the developed model.ResultsIn total, 2716 patients with NVUGIB were deemed eligible for participation. Following selection, 30 out of a total of 64 clinical parameters collected on day 1 after ICU admission remained associated with prognosis and were utilized for developing machine learning models. Among the 11 constructed models, the Gradient Boosting Decision Tree (GBDT) model demonstrated the best performance, achieving an AUC of 0.853 and an accuracy of 0.839 in the validation cohort. Feature importance analysis highlighted that shock, Glasgow Coma Scale (GCS), renal disease, age, albumin, and alanine aminotransferase (ALP) were the top six features of the GBDT model with the most significant impact. Furthermore, SHAP force analysis illustrated how the constructed model visualized the individualized prediction of death.ConclusionsPatient data from the MIMIC database were leveraged to develop a robust prognostic model for patients with NVUGIB in the ICU. The analysis using SHAP also assisted clinicians in gaining a deeper understanding of the disease.

Project description:BACKGROUND:Majority burn mortality prognostic scores were developed and validated in western populations. The primary objective of this study was to evaluate and identify possible risk factors which may be used to predict burns mortality in a local Malaysian burns intensive care unit. The secondary objective was to validate the five well known burn prognostic scores (Baux score, Abbreviated Burn Severity Index (ABSI) score, Ryan score, Belgium Outcome Burn Injury (BOBI) score and revised Baux score) to predict burn mortality prediction. METHODS:Patients that were treated at the Hospital Sultan Ismail's Burns Intensive Care (BICU) unit for acute burn injuries between 1 January 2010 to 31 December 2017 were included. Risk factors to predict in-patient burn mortality were gender, age, mechanism of injury, total body surface area burn (TBSA), inhalational injury, mechanical ventilation, presence of tracheotomy, time from of burn injury to BICU admission and initial centre of first emergency treatment was administered. These variables were analysed using univariate and multivariate analysis for the outcomes of death. All patients were scored retrospectively using the five-burn mortality prognostic scores. Predictive ability for burn mortality was analysed using the area under receiver operating curve (AUROC). RESULTS:A total of 525 patients (372 males and 153 females) with mean age of 34.5 ± 14.6 years were included. There were 463 survivors and 62 deaths (11.8% mortality rate). The outcome of the primary objective showed that amongst the burn mortality risk factors that remained after multivariate analysis were older age (p = 0.004), wider TBSA burn (p < 0.001) and presence of mechanical ventilation (p < 0.001). Outcome of secondary objective showed good AUROC value for the prediction of burn death for all five burn prediction scores (Baux score; AUROC:0.9, ABSI score; AUROC:0.92, Ryan score; AUROC:0.87, BOBI score; AUROC:0.91 and revised Baux score; AUROC:0.94). The revised Baux score had the best AUROC value of 0.94 to predict burns mortality. CONCLUSION:Current study evaluated and identified older age, total body surface area burns, and mechanical ventilation as significant predictors of burn mortality. In addition, the revised Baux score was the most accurate burn mortality risk score to predict mortality in a Malaysian burn's population.

Dataset Information

Predictors of mortality and endoscopic intervention in patients with upper gastrointestinal bleeding in the intensive care unit.

Publications

Predictors of mortality and endoscopic intervention in patients with upper gastrointestinal bleeding in the intensive care unit.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets